Avoiding strict saddle points of nonconvex regularized problems
From MaRDI portal
center stable manifold theoremiterative reweighted \(\ell_1\) algorithmnonconvex regularizationstrict saddle property
Nonsmooth analysis (49J52) Numerical methods of relaxation type (49M20) Numerical methods based on nonlinear programming (49M37) Numerical mathematical programming methods (65K05) Numerical optimization and variational techniques (65K10) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30)
Cites work
- A geometric analysis of phase retrieval
- A Newton-based method for nonconvex optimization with fast evasion of saddle points
- A proximal difference-of-convex algorithm with extrapolation
- Alternating Iteratively Reweighted Least Squares Minimization for Low-Rank Matrix Factorization
- An extrapolated iteratively reweighted \(\ell_1\) method with complexity analysis
- An unconstrained \(\ell_q\) minimization with \(0<q\leq 1\) for sparse solution of underdetermined linear systems
- Convergence of the reweighted \(\ell_1\) minimization algorithm for \(\ell_2-\ell_p\) minimization
- Convergence rate analysis of proximal iteratively reweighted \(\ell_1\) methods for \(\ell_p\) regularization problems
- Difference-of-convex learning: directional stationarity, optimality, and sparsity
- Efficient Reconstruction of Piecewise Constant Images Using Nonsmooth Nonconvex Minimization
- Enhancing sparsity by reweighted \(\ell _{1}\) minimization
- Escaping strict saddle points of the Moreau envelope in nonsmooth optimization
- Feature Selection via Mathematical Programming
- First-order methods almost always avoid strict saddle points
- Global convergence of proximal iteratively reweighted algorithm
- Group sparse optimization via \(\ell_{p,q}\) regularization
- scientific article; zbMATH DE number 3258063 (Why is no real title available?)
- Iterative \({\ell_1}\) minimization for non-convex compressed sensing
- Iterative reweighted minimization methods for \(l_p\) regularized unconstrained nonlinear programming
- Iteratively reweighted \(\ell _1\) algorithms with extrapolation
- Matrices
- Minimization of \(\ell_{1-2}\) for compressed sensing
- Nonconvex and nonsmooth sparse optimization via adaptively iterative reweighted methods
- On iteratively reweighted algorithms for nonsmooth nonconvex optimization in computer vision
- Optimality conditions and a smoothing trust region Newton method for nonlipschitz optimization
- Proximal methods avoid active strict saddles of weakly convex functions
- Relating _p regularization and reweighted _1 regularization
- Sparse Regularization: Convergence Of Iterative Jumping Thresholding Algorithm
- Stochastic subgradient descent escapes active strict saddles on weakly convex functions
This page was built for publication: Avoiding strict saddle points of nonconvex regularized problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7262232)
